An LLM (Large Language Model) is an artificial intelligence system trained on large amounts of data to understand and process language.
It generates responses by predicting, one element at a time, the most probable tokens based on the text it receives. It can write, summarize, translate, analyze documents, and produce code.
However, LLMs can generate incorrect or invented information. For this reason, in professional applications, outputs must be verified and the model must be integrated with suitable data, tools, and controls.